KGAT：Knowledge Graph Attention Network for Recommendation.pdf

Toprovidemoreaccurate,diverse,andexplainablerecommendation, it is compulsory to go beyond modeling user-item interactions andtakesideinformationintoaccount.Traditionalmethodslike factorizationmachine(FM)castitasasupervisedlearningproblem, whichassumeseachinteractionasanindependentinstancewith side information encoded. Due to the overlook of the relations amonginstancesoritems(e.g., thedirectorofamovieisalsoan actorofanothermovie),thesemethodsareinsufficienttodistillthe collaborativesignalfromthecollectivebehaviorsofusers.